Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for Manual Review of Rejected SAM 3 Access β Einsonx
Hello SAM 3 team,
My Hugging Face username is Einsonx. My previous request to access facebook/sam3 was rejected, and I would like to respectfully request a manual review.
I am a graduate of the Department of Mathematics at Zhejiang University and am currently conducting independent research in embodied AI. I hope to reproduce the ASPIRE framework on the LIBERO benchmark and subsequently investigate possible improvements to its task-program optimization, visual perception, and execution-failure analysis.
I plan to use SAM 3 as an auxiliary perception baseline for object segmentation and visual grounding in these reproduction and extension experiments. This is non-commercial research conducted locally using public or non-sensitive research data.
I will comply with the SAM License, privacy and data-protection requirements, export controls, and all prohibited-use restrictions. Could you please reconsider my request and reset or grant access to my Hugging Face account? Please let me know if any additional information is required.
Thank you.